My_Presentation.R

library(corrplot)

Error in library(corrplot) : there is no package called ‘corrplot’

mydata = read.csv("./ER-DataSet.csv")
mydata 

renamed_data = rename(mydata, 
                       Zip = Zip.Code, PCnty = Primary.County, Dual = Dual.Eligible, 
                       MDC = Major.Diagnostic.Category, EDC = Episode.Disease.Category, 
                      BC = Beneficiaries.with.Condition, 
                      BA = Beneficiaries.with.Admissions, 
                   TIA = Total.Inpatient.Admissions, 
                   TBERV = Beneficiaries.with.ER.Visits, 
                   TERV = Total.ER.Visits)
(renamed_data)

County enrollment missing!

(summary(renamed_data[c("Dual", "BC", "BA", "TIA", "TBERV", "TERV")]) )

       Dual             BC               BA               TIA             TBERV              TERV       
 Dual    :38324   Min.   :  21.0   Min.   :   0.00   Min.   :   0.0   Min.   :   0.00   Min.   :   0.0  
 Non-Dual:60367   1st Qu.:  32.0   1st Qu.:  14.00   1st Qu.:  25.0   1st Qu.:  13.00   1st Qu.:  33.0  
                  Median :  55.0   Median :  25.00   Median :  51.0   Median :  23.00   Median :  69.0  
                  Mean   : 139.1   Mean   :  50.54   Mean   : 111.5   Mean   :  56.41   Mean   : 172.3  
                  3rd Qu.: 120.0   3rd Qu.:  51.00   3rd Qu.: 113.0   3rd Qu.:  51.00   3rd Qu.: 162.0  
                  Max.   :7796.0   Max.   :1788.00   Max.   :4099.0   Max.   :3482.00   Max.   :8977.0  

outlier_out_data = filter(renamed_data, !BC%in% boxplot.stats(BC)$out,
               !BA%in% boxplot.stats(BA)$out,
               !TIA%in% boxplot.stats(TIA)$out,
               !TBERV%in% boxplot.stats(TBERV)$out,
               !TERV%in% boxplot.stats(TERV)$out
               )
plot_ly(outlier_out_data, x = ~Year, y = ~BC,  type = 'box', name = "BC") %>%
  add_trace(y = ~BA, name = "BA") %>%
  add_trace(y = ~TIA, name = "TIA") %>%
  add_trace(y = ~TBERV, name = "TBERV") %>%
  add_trace(y = ~TERV, name = "TERV") %>%
  layout(yaxis = list(title = ''), boxmode = 'group')

'layout' objects don't have these attributes: 'boxmode'
Valid attributes include:
'font', 'title', 'titlefont', 'autosize', 'width', 'height', 'margin', 'paper_bgcolor', 'plot_bgcolor', 'separators', 'hidesources', 'smith', 'showlegend', 'xaxis', 'yaxis', 'ternary', 'scene', 'geo', 'mapbox', 'radialaxis', 'angularaxis', 'direction', 'orientation', 'dragmode', 'hovermode', 'hoverlabel', 'legend', 'annotations', 'shapes', 'images', 'updatemenus', 'sliders', 'calendar', 'barmode', 'bargap', 'mapType'
'layout' objects don't have these attributes: 'boxmode'
Valid attributes include:
'font', 'title', 'titlefont', 'autosize', 'width', 'height', 'margin', 'paper_bgcolor', 'plot_bgcolor', 'separators', 'hidesources', 'smith', 'showlegend', 'xaxis', 'yaxis', 'ternary', 'scene', 'geo', 'mapbox', 'radialaxis', 'angularaxis', 'direction', 'orientation', 'dragmode', 'hovermode', 'hoverlabel', 'legend', 'annotations', 'shapes', 'images', 'updatemenus', 'sliders', 'calendar', 'barmode', 'bargap', 'mapType'

columns = data.frame(renamed_data[ , !names(renamed_data) %in% c("Year", "MDC", "EDC", "Zip", "PCnty", "Dual") ] )
ggpairs(columns )

 plot: [1,1] [===-----------------------------------------------------------------------------]  4% est: 0s 
 plot: [1,2] [======--------------------------------------------------------------------------]  8% est: 9s 
 plot: [1,3] [==========----------------------------------------------------------------------] 12% est: 7s 
 plot: [1,4] [=============-------------------------------------------------------------------] 16% est: 6s 
 plot: [1,5] [================----------------------------------------------------------------] 20% est: 5s 
 plot: [2,1] [===================-------------------------------------------------------------] 24% est: 4s 
 plot: [2,2] [======================----------------------------------------------------------] 28% est: 6s 
 plot: [2,3] [==========================------------------------------------------------------] 32% est: 5s 
 plot: [2,4] [=============================---------------------------------------------------] 36% est: 5s 
 plot: [2,5] [================================------------------------------------------------] 40% est: 4s 
 plot: [3,1] [===================================---------------------------------------------] 44% est: 4s 
 plot: [3,2] [======================================------------------------------------------] 48% est: 4s 
 plot: [3,3] [==========================================--------------------------------------] 52% est: 4s 
 plot: [3,4] [=============================================-----------------------------------] 56% est: 3s 
 plot: [3,5] [================================================--------------------------------] 60% est: 3s 
 plot: [4,1] [===================================================-----------------------------] 64% est: 2s 
 plot: [4,2] [======================================================--------------------------] 68% est: 2s 
 plot: [4,3] [==========================================================----------------------] 72% est: 2s 
 plot: [4,4] [=============================================================-------------------] 76% est: 2s 
 plot: [4,5] [================================================================----------------] 80% est: 2s 
 plot: [5,1] [===================================================================-------------] 84% est: 1s 
 plot: [5,2] [======================================================================----------] 88% est: 1s 
 plot: [5,3] [==========================================================================------] 92% est: 1s 
 plot: [5,4] [=============================================================================---] 96% est: 0s 
 plot: [5,5] [================================================================================]100% est: 0s 
                                                                                                            

corrplot(   cor(renamed_data[c("BC", "BA", "TIA", "TBERV", "TERV")])  )

d_stan = as.data.frame(scale(renamed_data[c("BC", "BA", "TIA", "TBERV", "TERV")]))
res1b = factanal(d_stan, factors = 2, rotation = "none", na.action = na.omit)
res1b$loadings

Loadings:
      Factor1 Factor2
BC     0.925         
BA     0.960  -0.270 
TIA    0.915  -0.200 
TBERV  0.963   0.260 
TERV   0.918   0.273 

               Factor1 Factor2
SS loadings      4.385   0.255
Proportion Var   0.877   0.051
Cumulative Var   0.877   0.928

summary(renamed_data[5])

                                                  MDC       
 Diabetes Mellitus                                  :11416  
 Diseases And Disorders Of The Cardiovascular System:30294  
 Diseases And Disordes Of The Respiratory System    :11329  
 HIV Infection                                      : 1077  
 Mental Diseases And Disorders                      :32481  
 Newborns And Other Neonates                        :   86  
 Substance Abuse                                    :12008  

ax_data = renamed_data
levels(ax_data$MDC) <- c("Diabetes", "Cardiovascular", "Respiratory ", 
        
                                          "HIV", "Mental", "Newborns", "Subtnc-Abuse")
plot_ly(ax_data, x = ~MDC) %>% 
  layout(title = "Frequency of Each Categor", 
         yaxis = list(title = ''), xaxis = list(title = "", tickangle = 45), 
               margin = list(b = 250))

No trace type specified:
  Based on info supplied, a 'histogram' trace seems appropriate.
  Read more about this trace type -> https://plot.ly/r/reference/#histogram
No trace type specified:
  Based on info supplied, a 'histogram' trace seems appropriate.
  Read more about this trace type -> https://plot.ly/r/reference/#histogram

plot_ly(renamed_data, x = ~MDC) %>% 
  layout(title = "Frequency of Each Categor", 
         yaxis = list(title = ''), xaxis = list(title = "", tickangle = 45), 
               margin = list(b = 250))

No trace type specified:
  Based on info supplied, a 'histogram' trace seems appropriate.
  Read more about this trace type -> https://plot.ly/r/reference/#histogram
No trace type specified:
  Based on info supplied, a 'histogram' trace seems appropriate.
  Read more about this trace type -> https://plot.ly/r/reference/#histogram

MDC_Dual = renamed_data[, c("MDC", "Dual")] %>% 
  group_by(MDC, Dual) %>% summarise(n()) 
colnames(MDC_Dual) = c("MDC", "Dual", "Frequency")
levels(MDC_Dual$MDC) <- c("Diabetes", "Cardiovascular", "Respiratory ", 
        
                                          "HIV", "Mental", "Newborns", "Subtnc-Abuse")
plot_ly(MDC_Dual, x = ~MDC, y = ~Frequency, color = ~Dual) %>% 
layout(title = "Frequency vs Dual Eligiblity", 
         yaxis = list(title = ''), xaxis = list(title = "", tickangle = 45), 
               margin = list(b = 250))

No trace type specified:
  Based on info supplied, a 'bar' trace seems appropriate.
  Read more about this trace type -> https://plot.ly/r/reference/#bar
minimal value for n is 3, returning requested palette with 3 different levels
No trace type specified:
  Based on info supplied, a 'bar' trace seems appropriate.
  Read more about this trace type -> https://plot.ly/r/reference/#bar
minimal value for n is 3, returning requested palette with 3 different levels

by_Dual_data = renamed_data[, c("Dual", "BC", "BA", "TIA", "TBERV", "TERV")] %>% 
  group_by(Dual) %>% 
        summarise( BC = sum(BC), BA = sum(BA), 
                   TIA = sum(TIA), 
                   TBERV = sum(TBERV), 
                   TERV = sum(TERV))
t <- list(  family = "sans serif",   size = 14,   color = 'blue')
plot_ly(by_Dual_data, x = ~Dual, y = ~BC,  type = 'bar', name = "BC") %>% 
  add_trace(y = ~BA, name = "BA") %>% 
  add_trace(y = ~TIA, name = "TIA") %>% 
  add_trace(y = ~TBERV, name = "TBERV") %>% 
  add_trace(y = ~TERV, name = "TERV") %>% 
  layout( title = "Population Count", 
          font = t, 
          yaxis = list(title = ''), xaxis = list(title = ""), barmode = 'group') 

ui <- fluidPage( 
  selectInput("categ", "Name of Category",
               c("Diabetes Mellitus" ,
                 "Diseases And Disorders Of The Cardiovascular System", 
                 "Diseases And Disordes Of The Respiratory System", 
                 "HIV Infection", 
                 "Mental Diseases And Disorders",
                 "Newborns And Other Neonates",
                 "Substance Abuse" 
                 )) 
  , # Now outputs
  plotlyOutput("my_plot_name")
  
 
  )
 server <- function(input, output) {
  
  output$my_plot_name <- 
    
    renderPlotly({   
      
    MDC_EDC = renamed_data[, c("MDC", "EDC")] %>%  filter(MDC == input$categ  )
    MDC_EDC <- lapply(MDC_EDC, factor)
    EDC_factor = as.factor( unlist(MDC_EDC[2])  )
    df_EDC = data.frame(table(EDC_factor))
    names(df_EDC) <- c("EDC_Category", "Freq")
    
    plot_ly(df_EDC, x = ~EDC_Category, y = ~Freq, type = 'bar',  insidetextfont = list(color = '#FFFFFF'), hoverinfo = 'text') %>% 
  layout( title = paste("Category: ", input$categ), 
          xaxis = list(title = "", tickangle = 45), yaxis = list(title = ""), 
          margin = list(b = 200), 
          font = t   )
      })
  
 }
 shinyApp(server = server, ui = ui)

Listening on http://127.0.0.1:4860
Ignoring explicitly provided widget ID "10e426fd50fa"; Shiny doesn't use themIgnoring explicitly provided widget ID "10e428ee4343"; Shiny doesn't use them

runApp(list(
  ui = basicPage(
    #h2('The attrubutes to select'),
    checkboxGroupInput("columns","Select Columns",
                       choices = c("BC", "BA", "TIA", "TBERV", "TERV"), inline = T),
    plotlyOutput("my_plot_name")
  ),
  server = function(input, output) {
    output$my_plot_name <- renderPlotly({
      if( length(input$columns) == 0 ){
        plot_ly() %>% layout()
        #dfzero <- by_MDC_data[,c("MDC", "BC")]
        #names(dfzero) <- c("MDC", "BC")
        #plot_ly(dfzero, x = ~MDC, y = ~BC,  type = 'bar', name = "TERV") %>%
        #  layout(title = "Total count of each Categor",
        #      yaxis = list(title = ''), xaxis = list(title = ""), barmode = 'group')
      }
      #if(length(input$columns) == 1){
      #  cols <- c("MDC", input$columns)
      #  df <- data.frame(by_MDC_data[,cols])
      #  names(df) <- c("MDC", "input_col")
      #  plot_ly(df, x = ~MDC, y = ~input_col,  type = 'bar', name = "TERV") %>%
      #    layout(title = "Total count of each Categor",
      #        yaxis = list(title = ''), xaxis = list(title = "", tickangle = -90),
      #        margin = list(b = 200), barmode = 'group')
      #}
      else{
        cols <- c("MDC", input$columns)
        df <- data.frame(by_MDC_data)
        names(df) <- c("MDC", "BC", "BA", "TIA", "TBERV", "TERV")
        df$MDC <- factor(df$MDC, levels = df[["MDC"]])
        p = plot_ly(df,  x = ~MDC,  type = 'bar', name = "BC")   %>% 
          layout( title = "Total count of each Categor",
               yaxis = list(title = ''), xaxis = list(title = "", tickangle = 45),
               margin = list(b = 200),
               barmode = 'group')
        if ("BC" %in% cols){  p = add_trace(p, y = ~BC, name = "BC")}
        if ("BA" %in% cols){  p = add_trace(p, y = ~BA, name = "BA")}
        if ( "TIA" %in% cols){ p = add_trace(p, y = ~TIA, name = "TIA") }
        if ( "TBERV" %in% cols){ p = add_trace(p, y = ~TBERV, name = "TBERV") }
        if ( "TERV" %in% cols){ p = add_trace(p, y = ~TERV, name = "TERV") }
        p
      }
    })
  }
))

Listening on http://127.0.0.1:4860
Ignoring explicitly provided widget ID "10e42252220f"; Shiny doesn't use themNo trace type specified and no positional attributes specifiedNo trace type specified:
  Based on info supplied, a 'scatter' trace seems appropriate.
  Read more about this trace type -> https://plot.ly/r/reference/#scatter
No scatter mode specifed:
  Setting the mode to markers
  Read more about this attribute -> https://plot.ly/r/reference/#scatter-mode
Error in data.frame: object 'by_MDC_data' not foundStack trace (innermost first):
    80: data.frame
    79: "plotly"::"ggplotly" [#39]
    78: func
    77: origRenderFunc
    76: output$my_plot_name
     1: runApp
Error in data.frame: object 'by_MDC_data' not foundStack trace (innermost first):
    80: data.frame
    79: "plotly"::"ggplotly" [#39]
    78: func
    77: origRenderFunc
    76: output$my_plot_name
     1: runApp

detailed_data = read.csv("NewData_Detailed.csv")
detailed_data

selected_columns = detailed_data[, c("Year", "Zip.Code", "County", "Total.Beneficiaries")] %>% 
        rename(Zip = Zip.Code, PCnty = County, TB = Total.Beneficiaries)
joined_data = inner_join(renamed_data, selected_columns)

Joining, by = c("Year", "Zip", "PCnty")
Column `PCnty` joining factors with different levels, coercing to character vector

cnty_poplulation = detailed_data[, c("County",  "Total.Beneficiaries")] %>% 
  group_by(County) %>% summarise(TBC = sum(Total.Beneficiaries)) %>% 
    rename(PCnty = County)
joined_data = inner_join(joined_data, cnty_poplulation)

Joining, by = "PCnty"
Column `PCnty` joining character vector and factor, coercing into character vector

head(joined_data)

by_cnty_data = renamed_data[, c("PCnty", "BC","BA", "TIA" , "TBERV" , "TERV")]%>% 
  group_by(PCnty) %>% 
        summarise( BC = sum(BC), BA = sum(BA), 
                   TIA = sum(TIA), 
                   TBERV = sum(TBERV), 
                   TERV = sum(TERV))
(by_cnty_data)

ui <- fluidPage( 
  radioButtons("attr", "Name of Attribute",  c("BC","BA", "TIA" , "TBERV" , "TERV"), inline = TRUE), # Now outputs
  leafletOutput("mymap")   
  )
server <- function(input, output) {
  
  output$mymap <- renderLeaflet({   
    
    
    adjusted_data <- by_cnty_data[,c("PCnty", input$attr)]
    names(adjusted_data) <- c("NAME_2", "col_name")
    
    
    # get county level spatial polygons for the United States  
    counties <- getData("GADM", country = "USA", level = 2)
    
    # filter down to just New York State Counties
    counties <- counties[counties@data$NAME_1 == "New York",]
    bins <- c(0, 10, 20, 50, 100, 200, 500, 1000, Inf)
    pal <- colorBin("YlOrRd", domain = density, bins = bins)
    
    ## In our data we have St Lawrence but in our SP obkect we have Saint lawrence, so we 
    ## fix it by gsub()
    adjusted_data$NAME_2 = gsub("St Lawrence", "Saint Lawrence", adjusted_data$NAME_2)
    counties@data = left_join(counties@data, adjusted_data)
    
    
    
    
    state_popup <- paste0("<strong>County: </strong>", 
                          counties$NAME_2, 
                          "<br><strong>Attribute is : </strong>",  input$attr, 
                          "<br><strong> Value : </strong>", counties$col_name/100)
    
    counties %>% leaflet() %>% addTiles() %>% 
      addPolygons(
          fillColor = ~pal(col_name/100),
            weight = 2,
            opacity = 1,
            color = "blue", # we can change it or remove it
            dashArray = "3",
            fillOpacity = 0.7,
            highlight = highlightOptions(
              weight = 5,
              color = "#666",
              dashArray = "",
              fillOpacity = 0.7,
              bringToFront = TRUE), 
          popup = state_popup
      ) %>% 
      
      addLegend("bottomright", pal = pal, values = ~col_name/100,
          title = ,
          #labFormat = labelFormat(prefix = "$"),
          opacity = 1   
          )
    
    })
  
}
shinyApp(server = server, ui = ui)

Listening on http://127.0.0.1:4860
trying URL 'http://biogeo.ucdavis.edu/data/gadm2.8/rds/USA_adm2.rds'
Content type ' êãgþ' length 13943951 bytes (13.3 MB)
downloaded 13.3 MB

Joining, by = "NAME_2"
Joining, by = "NAME_2"
Joining, by = "NAME_2"

Combine Chroplothe and ShinyApp

# library(dplyr)
# MCD_cnty = renamed_data %>% filter(MDC == "Diabetes Mellitus") 
# MCD_cnty =   MCD_cnty[, c("PCnty", "BC","BA", "TIA" , "TBERV" , "TERV")] %>% 
#   group_by(PCnty) %>% summarise(BC = sum(BC), BC = sum(BC), BA = sum(BA), 
#                                 TIA = sum(TIA), TBERV = sum(TBERV), TERV = sum(TERV))
# MCD_cnty

Now we map MDC

ui <- fluidPage( 
  selectInput("attr", "Name of MDC Category",  
               c("Diabetes Mellitus",
                 "Diseases And Disorders Of The Cardiovascular System", 
                 "Diseases And Disordes Of The Respiratory System" , 
                 "HIV Infection" , 
                 "Mental Diseases And Disorders", 
                 "Newborns And Other Neonates", 
                 "Substance Abuse")
               ), # Now outputs
  selectInput("var", "Name of Attribute",  c("BC","BA", "TIA" , "TBERV" , "TERV")),
  leafletOutput("mymap")   
  )
server <- function(input, output) {
  
  output$mymap <- renderLeaflet({   
    
    MCD_cnty = joined_data %>% filter(MDC == input$attr) 
    MCD_cnty = MCD_cnty %>% mutate( BC = BC*10^3/TBC, BA = BA*10^3/TBC, TIA = TIA*10^3/TBC, 
                                    TBERV = TBERV*10^3/TBC, TERV = TERV*10^3/TBC)
    MCD_cnty =   MCD_cnty[, c("PCnty", "BC","BA", "TIA" , "TBERV" , "TERV")] %>% 
          group_by(PCnty) %>% summarise(BC = sum(BC), BA = sum(BA), 
                                TIA = sum(TIA), TBERV = sum(TBERV), TERV = sum(TERV)
                                )
    ## To keep it dafe: 
    #MCD_cnty = renamed_data %>% filter(MDC == input$attr) 
    #MCD_cnty =   MCD_cnty[, c("PCnty", "BC","BA", "TIA" , "TBERV" , "TERV")] %>% 
    #      group_by(PCnty) %>% summarise(BC = sum(BC), BC = sum(BC), BA = sum(BA), 
    #                            TIA = sum(TIA), TBERV = sum(TBERV), TERV = sum(TERV))
    
    
    adjusted_data <- MCD_cnty[,c("PCnty", input$var)]
    names(adjusted_data) <- c("NAME_2", "col_name")
    
    
    # get county level spatial polygons for the United States  
    counties <- getData("GADM", country = "USA", level = 2)
    
    # filter down to just New York State Counties
    counties <- counties[counties@data$NAME_1 == "New York",]
    bins <- c(0, 25, 45, 60, 80, 170, 250, 400, 700, Inf)
    pal <- colorBin("YlOrRd", domain = density, bins = bins)
    
    ## In our data we have St Lawrence but in our SP obkect we have Saint lawrence, so we 
    ## fix it by gsub()
    adjusted_data$NAME_2 = gsub("St Lawrence", "Saint Lawrence", adjusted_data$NAME_2)
    counties@data = left_join(counties@data, adjusted_data)
    
    
    
    #pal <- brewer.pal(15, "YlGnBu")
    
    
    
    state_popup <- paste0("<strong>County: </strong>", 
                          counties$NAME_2, 
                          "<br><strong>MDC category : </strong>",  input$attr, 
                          "<br><strong> Value per 1K : </strong>", round(counties$col_name, 3) ) 
    
    counties %>% leaflet() %>% addTiles() %>% 
      addPolygons(
          fillColor = ~pal(col_name), 
            weight = 2,
            opacity = 1,
            color = "blue", # we can change it or remove it
            dashArray = "3",
            fillOpacity = 0.7,
            highlight = highlightOptions(
              weight = 5,
              color = "#666",
              dashArray = "",
              fillOpacity = 0.7,
              bringToFront = TRUE), 
          popup = state_popup
      ) %>% 
      
      addLegend("bottomright", pal = pal, values = ~col_name,
          title = ,
          #labFormat = labelFormat(prefix = "$"),
          opacity = 1   
          )
    
    })
  
}
shinyApp(server = server, ui = ui)

Listening on http://127.0.0.1:4860
Joining, by = "NAME_2"
Joining, by = "NAME_2"
Joining, by = "NAME_2"

ui <- fluidPage( 
  selectInput("attr", "Name of MDC Category",  
               c("Diabetes Mellitus",
                 "Diseases And Disorders Of The Cardiovascular System", 
                 "Diseases And Disordes Of The Respiratory System" , 
                 "HIV Infection" , 
                 "Mental Diseases And Disorders", 
                 "Newborns And Other Neonates", 
                 "Substance Abuse")
               ), # Now outputs
  selectInput("var", "Name of Attribute",  c("BC","BA", "TIA" , "TBERV" , "TERV")),
  leafletOutput("mymap")   
  )



server <- function(input, output) {
  
  output$mymap <- renderLeaflet({   
    
    MCD_cnty = joined_data %>% filter(MDC == input$attr) 
    MCD_cnty = MCD_cnty %>% mutate( BC = BC*10^3/TBC, BA = BA*10^3/TBC, TIA = TIA*10^3/TBC, 
                                    TBERV = TBERV*10^3/TBC, TERV = TERV*10^3/TBC)
    MCD_cnty =   MCD_cnty[, c("PCnty", "BC","BA", "TIA" , "TBERV" , "TERV")] %>% 
          group_by(PCnty) %>% summarise(BC = sum(BC), BA = sum(BA), 
                                TIA = sum(TIA), TBERV = sum(TBERV), TERV = sum(TERV)
                                )
    ## To keep it dafe: 
    #MCD_cnty = renamed_data %>% filter(MDC == input$attr) 
    #MCD_cnty =   MCD_cnty[, c("PCnty", "BC","BA", "TIA" , "TBERV" , "TERV")] %>% 
    #      group_by(PCnty) %>% summarise(BC = sum(BC), BC = sum(BC), BA = sum(BA), 
    #                            TIA = sum(TIA), TBERV = sum(TBERV), TERV = sum(TERV))
    
    
    adjusted_data <- MCD_cnty[,c("PCnty", input$var)]
    names(adjusted_data) <- c("NAME_2", "col_name")
    
    
    # get county level spatial polygons for the United States  
    counties <- getData("GADM", country = "USA", level = 2)
    
    # filter down to just New York State Counties
    counties <- counties[counties@data$NAME_1 == "New York",]
    bins <- c(0, 25, 45, 60, 80, 170, 250, 400, 700, Inf)
    pal <- colorBin("YlOrRd", domain = density, bins = bins)
    
    ## In our data we have St Lawrence but in our SP obkect we have Saint lawrence, so we 
    ## fix it by gsub()
    adjusted_data$NAME_2 = gsub("St Lawrence", "Saint Lawrence", adjusted_data$NAME_2)
    counties@data = left_join(counties@data, adjusted_data)
    
    
    
    #pal <- brewer.pal(15, "YlGnBu")
    
    
    
    state_popup <- paste0("<strong>County: </strong>", 
                          counties$NAME_2, 
                          "<br><strong>MDC category : </strong>",  input$attr, 
                          "<br><strong> Value per 1K : </strong>", round(counties$col_name, 3) ) 
    
    counties %>% leaflet() %>% addTiles() %>% 
      addPolygons(
          fillColor = ~pal(col_name), 
            weight = 2,
            opacity = 1,
            color = "blue", # we can change it or remove it
            dashArray = "3",
            fillOpacity = 0.7,
            highlight = highlightOptions(
              weight = 5,
              color = "#666",
              dashArray = "",
              fillOpacity = 0.7,
              bringToFront = TRUE), 
          popup = state_popup
      ) %>% 
      
      addLegend("bottomright", pal = pal, values = ~col_name,
          title = ,
          #labFormat = labelFormat(prefix = "$"),
          opacity = 1   
          )
    
    })
  
}


shinyApp(server = server, ui = ui)

```